0.25
0.5
0.75
1.25
1.5
1.75
2
SC-Block: Supervised Contrastive Blocking within Entity Resolution Pipelines
Published on Jun 18, 202439 Views
Millions of websites use the schema.org vocabulary to annotate structured data describing products, local businesses, or events within their HTML pages. Integrating schema.org data from the Semantic
Related categories
Chapter list
SC Block: Supervised Contrastive Blocking within Entity Resolution pipelines00:00
Motivation00:14
Contributions00:56
WDC Block01:33
WDC Block: Creation (1/2)01:37
WDC Block: Creation (2/2)02:23
WDC Block: Statistics and Comparison03:47
SC Block: Supervised Contrastive Learning for Blocking05:25
Overview05:39
Record Serialization06:55
Training Data Preparation07:25
Supervised Contrastive Loss08:51
Nearest Neighbour Search09:49
Blocking only Evaluation10:25
SOTA Baseline Blockers10:33
Evaluation10:56
Fixed k (k=5) - 111:30
Fixed k (k=5) - 212:03
99.5% Recall on Validation Set - 112:30
99.5% Recall on Validation Set - 213:05
Evaluation within Entity Resolution Pipelines13:52
Entity Resolution Pipelines13:59
Pipeline Performance - 114:55
Pipeline Performance - 215:20
Impact of Training Time - 115:40
Impact of Training Time - 215:54
Conclusion - 116:05
Conclusion - 216:09
Thank you for your attention!16:39